R Notebook

# Load packages
library(ggplot2)
library(dplyr)
library(tidyr)
library(tidyverse)
library(plotly)

# Read datasets/confirmed_cases_worldwide.csv into confirmed_cases_worldwide
coronavirus <- read_csv("./data/coronavirus.csv")

Parsed with column specification:
cols(
  date = col_date(format = ""),
  province = col_logical(),
  country = col_character(),
  lat = col_double(),
  long = col_double(),
  type = col_character(),
  cases = col_double()
)
45800 parsing failures.
  row      col           expected  actual                     file
37001 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37002 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37003 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37004 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37005 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
..... ........ .................. ....... ........................
See problems(...) for more details.

head(coronavirus)

str(coronavirus)

tibble [157,000 × 7] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ date    : Date[1:157000], format: "2020-01-22" "2020-01-23" "2020-01-24" ...
 $ province: logi [1:157000] NA NA NA NA NA NA ...
 $ country : chr [1:157000] "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
 $ lat     : num [1:157000] 33.9 33.9 33.9 33.9 33.9 ...
 $ long    : num [1:157000] 67.7 67.7 67.7 67.7 67.7 ...
 $ type    : chr [1:157000] "confirmed" "confirmed" "confirmed" "confirmed" ...
 $ cases   : num [1:157000] 0 0 0 0 0 0 0 0 0 0 ...
 - attr(*, "problems")= tibble [45,800 × 5] (S3: tbl_df/tbl/data.frame)
  ..$ row     : int [1:45800] 37001 37002 37003 37004 37005 37006 37007 37008 37009 37010 ...
  ..$ col     : chr [1:45800] "province" "province" "province" "province" ...
  ..$ expected: chr [1:45800] "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" ...
  ..$ actual  : chr [1:45800] "Alberta" "Alberta" "Alberta" "Alberta" ...
  ..$ file    : chr [1:45800] "'./data/coronavirus.csv'" "'./data/coronavirus.csv'" "'./data/coronavirus.csv'" "'./data/coronavirus.csv'" ...
 - attr(*, "spec")=
  .. cols(
  ..   date = col_date(format = ""),
  ..   province = col_logical(),
  ..   country = col_character(),
  ..   lat = col_double(),
  ..   long = col_double(),
  ..   type = col_character(),
  ..   cases = col_double()
  .. )

# # See the result
bycountry <- coronavirus %>% 
  filter(type == "confirmed") %>%
  group_by(country) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases)

`summarise()` ungrouping output (override with `.groups` argument)

bycountry

confirmed_cases = coronavirus %>% 
  group_by(date) %>%
  filter(type == "confirmed") %>%
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

# confirmed_cases_china = coronavirus %>%
#   group_by(date) %>%
#   filter(country == "China", type == "confirmed")%>% 
#   summarize(cases = sum(cases)) %>%
#   mutate(cumsum = cumsum(cases))
# confirmed_cases_china



(confirmed_cases)

NA
NA
NA
NA
NA

coronavirus %>% 
  filter(date == max(date)) %>%
  select(country, type, cases) %>%
  group_by(country, type) %>%
  summarise(total_cases = sum(cases)) %>%
  pivot_wider(names_from = type,
              values_from = total_cases) %>%
  arrange(-confirmed)

`summarise()` regrouping output by 'country' (override with `.groups` argument)

coronavirus %>% 
  group_by(type, date) %>%
  summarise(total_cases = sum(cases)) %>%
  pivot_wider(names_from = type, values_from = total_cases) %>%
  arrange(date) %>%
  mutate(active = confirmed - death - recovered) %>%
  mutate(active_total = cumsum(active),
                recovered_total = cumsum(recovered),
                death_total = cumsum(death)) %>%
  plot_ly(x = ~ date,
                  y = ~ active_total,
                  name = 'Active', 
                  fillcolor = '#1f77b4',
                  type = 'scatter',
                  mode = 'none', 
                  stackgroup = 'one') %>%
  add_trace(y = ~ death_total, 
             name = "Death",
             fillcolor = '#E41317') %>%
  add_trace(y = ~recovered_total, 
            name = 'Recovered', 
            fillcolor = 'forestgreen') %>%
  layout(title = "Distribution of Covid19 Cases Worldwide",
         legend = list(x = 0.1, y = 0.9),
         yaxis = list(title = "Number of Cases"),
         xaxis = list(title = "Source: Johns Hopkins University Center for Systems Science and Engineering"))

`summarise()` regrouping output by 'type' (override with `.groups` argument)
`arrange_()` is deprecated as of dplyr 0.7.0.
Please use `arrange()` instead.
See vignette('programming') for more help
This warning is displayed once every 8 hours.
Call `lifecycle::last_warnings()` to see where this warning was generated.

conf_df <- coronavirus %>% 
  filter(type == "confirmed") %>%
  group_by(country) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases) %>%
  mutate(parents = "Confirmed") %>%
  ungroup() 

`summarise()` ungrouping output (override with `.groups` argument)

  
  plot_ly(data = conf_df,
          type= "treemap",
          values = ~total_cases,
          labels= ~ country,
          parents=  ~parents,
          domain = list(column=0),
          name = "Confirmed",
          textinfo="label+value+percent parent")

ggplot(confirmed_cases, aes(x = date, y = cum_cases)) +
  geom_line(aes(x = date, y = cum_cases)) +
  ylab("Cumulative confirmed cases")

Error in FUN(X[[i]], ...) : object 'cum_cases' not found

head(coronavirus)

coronavirus = tibble::rowid_to_column(coronavirus, "ID")
head(coronavirus)

# coronavirus = coronavirus %>%
#   group_by(ID) %>% 
#   mutate(cum_cases = cumsum(cases))
# coronavirus %>% head(70)

mutate(group_by(coronavirus, ID), cumsum = cumsum(cases))

# df <- data.frame(id = rep(1:3, each = 5),
#                  hour = rep(1:5, 3),
#                  value = sample(1:15))
# 
# mutate(group_by(df,id), cumsum=cumsum(value))

confirmed_cases_usa = coronavirus %>%
  group_by(date) %>%
  filter(country == "US", type == "confirmed")%>% 
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

confirmed_cases_usa

NA

plt_cum_confirmed_cases_usa <- ggplot(confirmed_cases_usa, aes(date, cumsum)) +
  geom_line() +
  ylab("Cumulative confirmed cases") 

# See the plot
plt_cum_confirmed_cases_usa

# Filter for USA, from Feb 15
usa_after_march1 <- confirmed_cases_usa %>%
  filter(date >= "2020-03-1")

# Using china_after_feb15, draw a line plot cum_cases vs. date
# Add a smooth trend line using linear regression, no error bars
ggplot(usa_after_march1, aes(date, cumsum)) +
  geom_line() +
  geom_smooth(method = "lm", formula = 'y ~ x', se = FALSE) +
  ylab("Cumulative confirmed cases")

confirmed_cases_china = coronavirus %>%
  group_by(date) %>%
  filter(country == "China", type == "confirmed")%>% 
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

confirmed_cases_china

confirmed_cases_china %>% 
  group_by(date) %>% 
  summarize(cases = sum(cases)) %>% 
  select(date, country, cases, cumsum)

`summarise()` ungrouping output (override with `.groups` argument)
Error: Can't subset columns that don't exist.
x Column `country` doesn't exist.

plt_cum_confirmed_cases_china <- ggplot(confirmed_cases_china, aes(date, cumsum)) +
  geom_line() +
  ylab("Cumulative confirmed cases") 

# See the plot
plt_cum_confirmed_cases_china

who_events <- tribble(
  ~ date, ~ event,
  "2020-01-30", "Global health emergency declared",
  "2020-03-11", "Pandemic declared",
  "2020-02-13", "China reporting change"
) %>%
  mutate(date = as.Date(date))

# Using who_events, add vertical dashed lines with an xintercept at date
# and text at date, labeled by event, and at 100000 on the y-axis
plt_cum_confirmed_cases_china + 
  geom_vline(aes(xintercept = date), data = who_events, linetype = "dashed") +
  geom_text(aes(x = date, label = event), data = who_events, y = 1e5)

# Filter for China, from Feb 15
china_after_feb15 <- confirmed_cases_china %>%
  filter(date >= "2020-02-15")

# Using china_after_feb15, draw a line plot cum_cases vs. date
# Add a smooth trend line using linear regression, no error bars
ggplot(china_after_feb15, aes(date, cumsum)) +
  geom_line() +
  geom_smooth(method = "lm", formula = 'y ~ x', se = FALSE) +
  ylab("Cumulative confirmed cases")

not_china = coronavirus %>%
  group_by(date) %>%
  filter(country != "China", type == "confirmed")%>% 
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

not_china

# not_china %>% 
#   group_by(date) %>% 
#   summarize(cases = sum(cases)) %>% 
#   select(date, country, cases, cumsum)


glimpse(not_china)

Rows: 200
Columns: 3
$ date   <date> 2020-01-22, 2020-01-23, 2020-01-24, 2020-01-25, 2020-01-26, 2020-01-27, 2…
$ cases  <dbl> 7, 4, 10, 7, 15, 7, 19, 10, 14, 32, 22, 10, 14, 20, 12, 12, 70, 30, 15, 84…
$ cumsum <dbl> 7, 11, 21, 28, 43, 50, 69, 79, 93, 125, 147, 157, 171, 191, 203, 215, 285,…

not_usa = coronavirus %>%

Warning messages:
1: In readChar(file, size, TRUE) : truncating string with embedded nuls
2: In readChar(file, size, TRUE) : truncating string with embedded nuls
3: In readChar(file, size, TRUE) : truncating string with embedded nuls
4: In readChar(file, size, TRUE) : truncating string with embedded nuls
5: In readChar(file, size, TRUE) : truncating string with embedded nuls
6: In readChar(file, size, TRUE) : truncating string with embedded nuls
7: In readChar(file, size, TRUE) : truncating string with embedded nuls

  group_by(date) %>%
  filter(country != "US", type == "confirmed")%>% 
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

not_usa

# Using not_usa, draw a line plot cum_cases vs. date
# Add a smooth trend line using linear regression, no error bars
plt_not_usa_trend_lin <- ggplot(not_usa, aes(date, cumsum)) +
  geom_line() +
  geom_smooth(method = "lm", formula = 'y ~ x', se = FALSE) +
  ylab("Cumulative confirmed cases")

# See the result
plt_not_usa_trend_lin 

not_china2 = coronavirus %>%
  group_by(date) %>%
  filter(country != "China", type == "confirmed")%>% 
  summarize(cases = sum(cases)) %>%
  mutate(cumsum = cumsum(cases))

`summarise()` ungrouping output (override with `.groups` argument)

not_china2

world_after_feb15 <- all_countries %>%
  filter(date >= "2020-02-15")

Error in eval(lhs, parent, parent) : object 'all_countries' not found

# Using not_china, draw a line plot cum_cases vs. date
# Add a smooth trend line using linear regression, no error bars
plt_not_china_trend_lin <- ggplot(not_china, aes(date, cumsum)) +
  geom_line() +
  geom_smooth(method = "lm", formula = 'y ~ x', se = FALSE) +
  ylab("Cumulative confirmed cases")

# See the result
plt_not_china_trend_lin 

plt_not_china_trend_lin + 
  scale_y_log10()

bycountry <- coronavirus %>% 
  mutate(date = as.Date(date))%>%
  filter(type == "confirmed") %>%
  group_by(country, date) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases)

`summarise()` regrouping output by 'country' (override with `.groups` argument)

Filter by top 7 countries

target = c("Brazil", "India", "Mexico", "Peru", "Russia", "South Africa", "US")
top_7countries = bycountry %>% 
  filter(country %in% target) %>% 
  filter(total_cases > 0)

top_7countries

NA

plt_top_7countries = ggplot(top_7countries, aes(date, total_cases))  +
    geom_line(aes(group = country, color = country))+
    ylab("Cumulative confirmed cases")

plt_top_7countries

plt_top_7countries + 
  scale_y_log10()

ggplot(top_7countries, aes(x= country, y = total_cases))  +
    geom_boxplot(aes(color = country))

income_hist = clean %>% filter(top_7countries, country =='US') %>% 
  ggplot(., aes(x=total_cases)) +
  geom_histogram(bins=8) +
  theme_bw()

Error in eval(lhs, parent, parent) : object 'clean' not found

ui <- fluidPage(
  # CODE BELOW: Add a titlePanel with an appropriate title
  titlePanel("COVID-19"),
  # REPLACE CODE BELOW: with theme = shinythemes::shinytheme("<your theme>")
  theme = shinythemes::shinytheme("cerulean"),
  # shinythemes::themeSelector(),
  sidebarLayout(
    sidebarPanel(
      selectInput('country', 'Select Country', top_7countries$country, multiple = TRUE),
      dateRangeInput("date", "Select a Date Range", 
                     start = "2020-02-15",
                     end = "2020-08-15")
    ),
    mainPanel(
      tabsetPanel(
        tabPanel('Plot', plotly::plotlyOutput('plot_top_7countries')),
        tabPanel('Table', DT::DTOutput('table_top_7countries'))
      )
    )
  )
)
server <- function(input, output, session){
  # Function to plot trends in a name
  plot_trends <- function(){
     top_7countries %>%  
      filter(country == input$country, date >= "2020-02-15") %>% 
      ggplot(aes(x = date, y = total_cases)) +
      geom_line()
  }
  output$plot_top_7countries <- plotly::renderPlotly({
    validate(
    need(input$country != "", "Select a country and date range to get the app working")
    )
    plot_trends()
  })
  
  output$table_top_7countries <- DT::renderDT({
    top_7countries %>% 
      filter(country == input$country)
  })
}
shinyApp(ui = ui, server = server)

Listening on http://127.0.0.1:6288

NA

# Group by country, summarize to calculate total cases, find the top 7
coronavirus <- read_csv("./data/coronavirus.csv")

Parsed with column specification:
cols(
  date = col_date(format = ""),
  province = col_logical(),
  country = col_character(),
  lat = col_double(),
  long = col_double(),
  type = col_character(),
  cases = col_double()
)
45800 parsing failures.
  row      col           expected  actual                     file
37001 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37002 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37003 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37004 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
37005 province 1/0/T/F/TRUE/FALSE Alberta './data/coronavirus.csv'
..... ........ .................. ....... ........................
See problems(...) for more details.

bycountry <- coronavirus %>% 
  mutate(date = as.Date(date))%>%
  filter(type == "confirmed") %>%
  group_by(country, date) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases)

`summarise()` regrouping output by 'country' (override with `.groups` argument)

target = c("Brazil", "India", "Mexico", "Peru", "Russia", "South Africa", "US")
top_7countries = bycountry %>% 
  filter(country %in% target) %>% 
  filter(total_cases > 0)

top_7countries

ui <- fluidPage(
  # CODE BELOW: Add a titlePanel with an appropriate title
  titlePanel("COVID-19"),
  # REPLACE CODE BELOW: with theme = shinythemes::shinytheme("<your theme>")
  theme = shinythemes::shinytheme("superhero"),
  
  sidebarLayout(
    sidebarPanel(
      selectInput('country', 'Select Country', top_7countries$country, multiple = TRUE),
      dateRangeInput("date", "Select a Date Range", 
                     start = "2020-02-15",
                     end = "2020-08-15")
    ),
    mainPanel(
      tabsetPanel(
        tabPanel('Plot', plotly::plotlyOutput('plot_top_7countries')),
        tabPanel('Table', DT::DTOutput('table_top_7countries'))
      )
    )
  )
)
server <- function(input, output, session){
  # Function to plot trends in a name
  plot_trends <- function(){
     top_7countries %>%  
      filter(country == input$country, date >= "2020-02-15") %>% 
      ggplot(aes(x = date, y = total_cases)) +
      geom_line()
  }
  output$plot_top_7countries <- plotly::renderPlotly({
    validate(
    need(input$country != "", "Select a country and date range to get the app working")
    )
    plot_trends()
  })
  
  output$table_top_7countries <- DT::renderDT({
    top_7countries %>% 
      filter(country == input$country)
  })
}
shinyApp(ui = ui, server = server)

Listening on http://127.0.0.1:6288

NA

# Group by country, summarize to calculate total cases, find the top 7
owid_covid <- read_csv("./data/owid-covid-data.csv")

Parsed with column specification:
cols(
  .default = col_double(),
  iso_code = col_character(),
  continent = col_character(),
  location = col_character(),
  date = col_date(format = ""),
  new_tests = col_logical(),
  total_tests = col_logical(),
  total_tests_per_thousand = col_logical(),
  new_tests_per_thousand = col_logical(),
  new_tests_smoothed = col_logical(),
  new_tests_smoothed_per_thousand = col_logical(),
  tests_per_case = col_logical(),
  positive_rate = col_logical(),
  tests_units = col_logical()
)
See spec(...) for full column specifications.
108700 parsing failures.
 row                      col           expected        actual                         file
1169 new_tests                1/0/T/F/TRUE/FALSE 2.0           './data/owid-covid-data.csv'
1169 total_tests              1/0/T/F/TRUE/FALSE 2.0           './data/owid-covid-data.csv'
1169 total_tests_per_thousand 1/0/T/F/TRUE/FALSE 0.0           './data/owid-covid-data.csv'
1169 new_tests_per_thousand   1/0/T/F/TRUE/FALSE 0.0           './data/owid-covid-data.csv'
1169 tests_units              1/0/T/F/TRUE/FALSE people tested './data/owid-covid-data.csv'
.... ........................ .................. ............. ............................
See problems(...) for more details.

owid_bycountry = owid_covid %>% 
  group_by(location, date) %>%
  summarize(total_cases = sum(total_cases)) 

`summarise()` regrouping output by 'location' (override with `.groups` argument)

owid_bycountry

target = c("Brazil", "India", "Mexico", "Peru", "Russia", "South Africa", "United States")
top_7countries_OW = owid_bycountry %>% 
  group_by(location) %>% 
  filter(location %in% target) %>% 
  filter(total_cases > 0)

top_7countries_OW

ui <- fluidPage(
  # CODE BELOW: Add a titlePanel with an appropriate title
  titlePanel("COVID-19"),
  # REPLACE CODE BELOW: with theme = shinythemes::shinytheme("<your theme>")
  theme = shinythemes::shinytheme("cerulean"),
  # shinythemes::themeSelector(),
  sidebarLayout(
    sidebarPanel(
      selectInput('location', 'Select Country', top_7countries_OW$location),
  #     sliderInput("month", "Select Month:",
  #   min = 2, max = 8, value = 4, 
  # )
      selectInput('month','Select Month', top_7countries_OW$month, multiple = TRUE)
    ),
  
    mainPanel(
      tabsetPanel(
        tabPanel('Plot', plotly::plotlyOutput('plot_top_7countries_OW')),
        tabPanel('Table', DT::DTOutput('table_top_7countries_OW'))
      )
    )
  )
)
server <- function(input, output, session){
  # Function to plot trends in a name
  plot_trends <- function(){
     top_7countries_OW %>%  
      filter(location == input$location) %>% 
      filter(month == input$month) %>% 
      ggplot(aes(x = date, y = total_cases)) +
      geom_line()
  }
  output$plot_top_7countries_OW <- plotly::renderPlotly({
    validate(
    need(input$location != "", "Select a country to get the app working")
    )
    plot_trends()
  })
  
  output$table_top_7countries_OW <- DT::renderDT({
    top_7countries_OW %>% 
      filter(location == input$location)%>% 
      filter(month == input$month) %>% 
      select(location, date, total_cases)
  })
}
shinyApp(ui = ui, server = server)

Listening on http://127.0.0.1:6288
Error in : Problem with `filter()` input `..1`.
x Input `..1` must be of size 194 or 1, not size 0.
ℹ Input `..1` is `month == input$month`.
ℹ The error occured in group 1: location = "Italy".  124: <Anonymous>

NA

ui <- fluidPage(
  # set theme
  theme = shinythemes::shinytheme("cerulean"),
  # shinythemes::themeSelector(),
  
  ## attempt to create multi pages
  tags$head(
  tags$style(HTML("
          .navbar .navbar-header {float: right}
        ")) 
  ),
  
  navbarPage("WORLD", icon=icon('globe'),
    title="COVID-19 Worldwide by the Numbers",
    id="nav",
    position="fixed-top",
    collapsible=TRUE,
             br(),
             br(),
             br(),
             fluidRow(h1("World COVID-19 numbers by Month")),
          fluidRow(
  
  sidebarLayout(
    sidebarPanel(
      selectInput('location', 'Select Country', top_7countries_OW$location),
  #     sliderInput("month", "Select Month:",
  #   min = 2, max = 8, value = 4, 
  # )
      selectInput('month','Select Month', top_7countries_OW$month, multiple = TRUE)
    ),
  
    mainPanel(
      tabsetPanel(
        tabPanel('Plot', plotly::plotlyOutput('plot_top_7countries_OW')),
        tabPanel('Table', DT::DTOutput('table_top_7countries_OW'))
      )
    )
  )
)
), #end of first tabPanel
navbarMenu("EXPLORE", icon=icon('compass'),
                        br(),
                        br(),
                        br(),
                        fluidRow(h1("Renewable Energy Insights by Region")),
                        fluidRow( 
    sidebarLayout(
    sidebarPanel(
      selectInput('location', 'Select Country', top_7countries_OW$location),
      sliderInput("month", "Select Month:",
    min = 2, max = 8, value = 4,
  ),
    #   selectInput('month','Select Month', top_7countries_OW$month, multiple = TRUE)
    # ),
  
    mainPanel(
      tabsetPanel(
        tabPanel('Plot', plotly::plotlyOutput('plot_top_7countries_OW')),
        tabPanel('Table', DT::DTOutput('table_top_7countries_OW'))
      )
    )
  )
)
           
)
)
)

Error in buildTabset(tabs, "nav navbar-nav", NULL, id, selected) : 
  Tabs should all be unnamed arguments, but some are named: icon